Triple
T34157528
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samuel Scudder |
E876180
|
entity |
| Predicate | successorAsMirrorMaster |
P201149
|
FINISHED |
| Object | Evan McCulloch |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Evan McCulloch | Statement: [Samuel Scudder, successorAsMirrorMaster, Evan McCulloch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorAsMirrorMaster Context triple: [Samuel Scudder, successorAsMirrorMaster, Evan McCulloch]
-
A.
regardsAsRightfulSuccessorOf
Indicates that one entity recognizes or treats another entity as the legitimate heir or next in line to assume a particular role, position, or status.
-
B.
intendedSuccessorTo
Indicates that one entity is meant or designated to follow, replace, or take over the role or position of another entity in the future.
-
C.
successorDesignated
Indicates that one entity has been formally chosen or named to take over the role, position, or responsibilities of another entity in the future.
-
D.
successorModel
Indicates that one model is the direct follow-up or replacement for another earlier model.
-
E.
successorRole
Indicates that one role or position directly follows and replaces another in a sequence or organizational structure.
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f349ac987481908a8e6053f665bc8b |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ffcc6182b48190afb598ced6500e66 |
completed | May 10, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69ffcbb363748190bc6f8d038fba44ff |
completed | May 10, 2026, 12:05 a.m. |
| PDg | Predicate description generation | batch_69ffcc60dae48190b76b3eb7e2ce5103 |
completed | May 10, 2026, 12:08 a.m. |
Created at: May 1, 2026, 1:54 a.m.